Prognosis of prostate gland morphology study using artificial neural network
The research goal is to optimize the management of patients with serum PSA level falling in the range of 4-10 ng/ ml by designing and educating of an artificial neural network, which may be used to predict prostate gland morphology basing on clinical, laboratory and imaging data. Material and method...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Saratov State Medical University
2014-06-01
|
| Series: | Саратовский научно-медицинский журнал |
| Subjects: | |
| Online Access: | http://www.ssmj.ru/system/files/2014_02_328-332.pdf |
| _version_ | 1818896438158950400 |
|---|---|
| author | Popkov V.M. Shatylko T.V. Fomkin R.N. |
| author_facet | Popkov V.M. Shatylko T.V. Fomkin R.N. |
| author_sort | Popkov V.M. |
| collection | DOAJ |
| description | The research goal is to optimize the management of patients with serum PSA level falling in the range of 4-10 ng/ ml by designing and educating of an artificial neural network, which may be used to predict prostate gland morphology basing on clinical, laboratory and imaging data. Material and methods. Data of 254 patients, who were admitted to the oncological Department of S. R. Mirotvortsev Clinical hospital for transrectal prostate biopsy, was collected to construct several artificial neural networks with different architecture. External validation was performed on 27 patients, who had prostate biopsy in January-February 2014. Results. One-layer network, consisting of 11 input, 9 hidden and 3 output neurons, was determined to be the most successful: in 92.6% cases it was correct in predicting prostate cancer or its absence. Input factors were evaluated according to their relative importance, from more important to less important: prostate volume, serum PSA, patient's age, prostate consistency, PSA velocity, prostate symmetry, previous negative biopsy, free serum PSA, intake of 5-alpha-reductase inhibitors. Conclusion. Artificial neural networks may be used to predict morphological findings in prostate biopsy. High PSA density and firm prostate consistency should cause suspicion of prostate cancer. |
| first_indexed | 2024-12-19T19:00:17Z |
| format | Article |
| id | doaj.art-3e2a9779a49145d6a6950fd08a0bb1b5 |
| institution | Directory Open Access Journal |
| issn | 2076-2518 |
| language | Russian |
| last_indexed | 2024-12-19T19:00:17Z |
| publishDate | 2014-06-01 |
| publisher | Saratov State Medical University |
| record_format | Article |
| series | Саратовский научно-медицинский журнал |
| spelling | doaj.art-3e2a9779a49145d6a6950fd08a0bb1b52022-12-21T20:09:34ZrusSaratov State Medical UniversityСаратовский научно-медицинский журнал2076-25182014-06-011023283323710Prognosis of prostate gland morphology study using artificial neural networkPopkov V.M.0Shatylko T.V.1Fomkin R.N.2Saratov State Medical UniversitySaratov State Medical UniversitySaratov State Medical UniversityThe research goal is to optimize the management of patients with serum PSA level falling in the range of 4-10 ng/ ml by designing and educating of an artificial neural network, which may be used to predict prostate gland morphology basing on clinical, laboratory and imaging data. Material and methods. Data of 254 patients, who were admitted to the oncological Department of S. R. Mirotvortsev Clinical hospital for transrectal prostate biopsy, was collected to construct several artificial neural networks with different architecture. External validation was performed on 27 patients, who had prostate biopsy in January-February 2014. Results. One-layer network, consisting of 11 input, 9 hidden and 3 output neurons, was determined to be the most successful: in 92.6% cases it was correct in predicting prostate cancer or its absence. Input factors were evaluated according to their relative importance, from more important to less important: prostate volume, serum PSA, patient's age, prostate consistency, PSA velocity, prostate symmetry, previous negative biopsy, free serum PSA, intake of 5-alpha-reductase inhibitors. Conclusion. Artificial neural networks may be used to predict morphological findings in prostate biopsy. High PSA density and firm prostate consistency should cause suspicion of prostate cancer.http://www.ssmj.ru/system/files/2014_02_328-332.pdfartificial neural networksprostate cancerPSA |
| spellingShingle | Popkov V.M. Shatylko T.V. Fomkin R.N. Prognosis of prostate gland morphology study using artificial neural network Саратовский научно-медицинский журнал artificial neural networks prostate cancer PSA |
| title | Prognosis of prostate gland morphology study using artificial neural network |
| title_full | Prognosis of prostate gland morphology study using artificial neural network |
| title_fullStr | Prognosis of prostate gland morphology study using artificial neural network |
| title_full_unstemmed | Prognosis of prostate gland morphology study using artificial neural network |
| title_short | Prognosis of prostate gland morphology study using artificial neural network |
| title_sort | prognosis of prostate gland morphology study using artificial neural network |
| topic | artificial neural networks prostate cancer PSA |
| url | http://www.ssmj.ru/system/files/2014_02_328-332.pdf |
| work_keys_str_mv | AT popkovvm prognosisofprostateglandmorphologystudyusingartificialneuralnetwork AT shatylkotv prognosisofprostateglandmorphologystudyusingartificialneuralnetwork AT fomkinrn prognosisofprostateglandmorphologystudyusingartificialneuralnetwork |